Commit Graph

183 Commits

Author SHA1 Message Date
Ivan Voras
630db7f99b The hardware has caught up; improvements are now observed even at 128,
but stay conservative and bump read_max to "only" 64 (it will probably be
a good idea to increase this to 128 after the next major release).
2011-03-16 16:22:59 +00:00
Ivan Voras
e98c5c7813 Bumping the read-ahead count once more, to value equivalent to 512 KiB on
most system, based on benchmark results on a low-end fibre channel SAN
under VMWare:

vfs.read_max		read performance
8  (historical default)	83 MB/s
16 (recent bump)	131 MB/s
32 (this version)	152 MB/s
64			157 MB/s

(results are +/- 3 MB/s)

As read-ahead is heuristic, based on past IO requests, it shouldn't be
problematic. The new default is still smaller then in other OSes.
2010-08-09 22:56:10 +00:00
Ivan Voras
27f11235b9 To help with sequential read UFS performance on modern systems, increase
the vfs.read_max default. For most systems this means going from 128 KiB
to 256 KiB, which is still very conservative and lower than what most
other operating systems use, but as a sane default should not
interfere much with existing systems.

For systems with RAID volumes and/or virtualization envirnments, where
read performance is very important, increasing this sysctl tunable to 32
or even more will demonstratively yield additional performance benefits.

If MAXPHYS ever gets bumped up, it will probably be a good idea to slave
read_max to it.
2010-08-07 18:30:10 +00:00
Alan Cox
9785747f87 Remove a stale comment. The very same revision (r85511) that introduced
this comment also implemented the proposed change to the code.

Approved by:	re (kib)
2009-06-30 19:39:17 +00:00
Alan Cox
de0c3e0895 Correct a long-standing performance bug in cluster_rbuild(). Specifically,
in the case of a file system with a block size that is less than the page
size, cluster_rbuild() looks at too many of the page's valid bits.
Consequently, it may terminate prematurely, resulting in poor performance.

Reported by:	bde
Reviewed by:	tegge
Approved by:	re (kib)
2009-06-27 21:37:36 +00:00
Alan Cox
0a2e596a93 Eliminate unnecessary obfuscation when testing a page's valid bits. 2009-06-07 19:38:26 +00:00
Jeff Roberson
698b1a6643 - Complete part of the unfinished bufobj work by consistently using
BO_LOCK/UNLOCK/MTX when manipulating the bufobj.
 - Create a new lock in the bufobj to lock bufobj fields independently.
   This leaves the vnode interlock as an 'identity' lock while the bufobj
   is an io lock.  The bufobj lock is ordered before the vnode interlock
   and also before the mnt ilock.
 - Exploit this new lock order to simplify softdep_check_suspend().
 - A few sync related functions are marked with a new XXX to note that
   we may not properly interlock against a non-zero bv_cnt when
   attempting to sync all vnodes on a mountlist.  I do not believe this
   race is important.  If I'm wrong this will make these locations easier
   to find.

Reviewed by:	kib (earlier diff)
Tested by:	kris, pho (earlier diff)
2008-03-22 09:15:16 +00:00
Jeff Roberson
1c4bcd050a - Move rusage from being per-process in struct pstats to per-thread in
td_ru.  This removes the requirement for per-process synchronization in
   statclock() and mi_switch().  This was previously supported by
   sched_lock which is going away.  All modifications to rusage are now
   done in the context of the owning thread.  reads proceed without locks.
 - Aggregate exiting threads rusage in thread_exit() such that the exiting
   thread's rusage is not lost.
 - Provide a new routine, rufetch() to fetch an aggregate of all rusage
   structures from all threads in a process.  This routine must be used
   in any place requiring a rusage from a process prior to it's exit.  The
   exited process's rusage is still available via p_ru.
 - Aggregate tick statistics only on demand via rufetch() or when a thread
   exits.  Tick statistics are kept in the thread and protected by sched_lock
   until it exits.

Initial patch by:	attilio
Reviewed by:		attilio, bde (some objections), arch (mostly silent)
2007-06-01 01:12:45 +00:00
Wojciech A. Koszek
59f65a4ba6 Change these descriptions of memory types used in malloc(9), as their
current, rather long strings make output from vmstat -m look unpleasant.

Approved by:	cognet (mentor)
2007-03-05 00:21:40 +00:00
Alan Cox
9af80719db Replace PG_BUSY with VPO_BUSY. In other words, changes to the page's
busy flag, i.e., VPO_BUSY, are now synchronized by the per-vm object
lock instead of the global page queues lock.
2006-10-22 04:28:14 +00:00
Tor Egge
a1e363f256 Add mnt_noasync counter to better handle interleaved calls to nmount(),
sync() and sync_fsync() without losing MNT_ASYNC.  Add MNTK_ASYNC flag
which is set only when MNT_ASYNC is set and mnt_noasync is zero, and
check that flag instead of MNT_ASYNC before initiating async io.
2006-09-26 04:15:59 +00:00
Tor Egge
41d7199b9d Remove unused leaked debug function prototype. 2006-03-21 01:04:24 +00:00
Tor Egge
7de3839d0d Let snapshots make a copy of old contents for all buffers taking part in a
cluster instead of just the first buffer.

Delay buf_start() calls until snapshots have a copy of old content.

PR:		kern/93942
2006-03-19 21:43:36 +00:00
Craig Rodrigues
6951bea6c8 Changes imported from XFS for FreeBSD project:
- add fields to struct buf (needed by XFS)
    - 3 private fields: b_fsprivate1, b_fsprivate2, b_fsprivate3
    - b_pin_count, count of pinned buffer

- add new B_MANAGED flag
- add breada() function to initiate asynchronous I/O on read-ahead blocks.
- add bufdone_finish(), bpin(), bunpin_wait() functions

Patches provided by:	kan
Reviewed by:		phk
Silence on:		arch@
2005-12-07 03:39:08 +00:00
Robert Watson
5bb84bc84b Normalize a significant number of kernel malloc type names:
- Prefer '_' to ' ', as it results in more easily parsed results in
  memory monitoring tools such as vmstat.

- Remove punctuation that is incompatible with using memory type names
  as file names, such as '/' characters.

- Disambiguate some collisions by adding subsystem prefixes to some
  memory types.

- Generally prefer lower case to upper case.

- If the same type is defined in multiple architecture directories,
  attempt to use the same name in additional cases.

Not all instances were caught in this change, so more work is required to
finish this conversion.  Similar changes are required for UMA zone names.
2005-10-31 15:41:29 +00:00
Stephan Uphoff
198b0a3b71 Only set B_RAM (Read ahead mark) on an incore buffers if we can lock it.
This fixes a race condition caused by the unlocked write access to the
b_flags field.

MFC after:	3 days
2005-10-24 14:23:04 +00:00
Alexander Kabaev
857b66d505 Do not use vm_pager_init() to initialize vnode_pbuf_freecnt variable.
vm_pager_init() is run before required nswbuf variable has been set
to correct value. This caused system to run with single pbuf available
for vnode_pager. Handle both cluster_pbuf_freecnt and vnode_pbuf_freecnt
variable in the same way.

Reported by:	ade
Obtained from:	alc
MFC after:	2 days
2005-08-13 20:21:33 +00:00
Alan Cox
7daa3570e4 Revert revision 1.164: pmap_qremove() does not require protection by
VM_LOCK_GIANT.

Discussed with: jeff
2005-05-14 05:09:11 +00:00
Jeff Roberson
8d46d9c46f - Remove spls and comments relating to them. 2005-05-01 01:01:17 +00:00
Jeff Roberson
4e0ed69694 - Call VM_LOCK_GIANT in cluster_callback() to protect some pmap calls. VFS
will not be acquiring Giant before calling this function anymore.

Sponsored by:	Isilon Systems, Inc.
2005-04-30 11:26:58 +00:00
Poul-Henning Kamp
502a590bf1 make cluster_callback() static 2005-02-10 12:17:48 +00:00
Jeff Roberson
791625d853 - Remove GIANT_REQUIRED where giant is no longer required.
Sponsored By:	Isilon Systems, Inc.
2005-01-24 10:33:46 +00:00
Alan Cox
956d03da83 Eliminate (now) unnecessary acquisition and release of the global page
queues lock.
2004-12-29 04:49:10 +00:00
Poul-Henning Kamp
ce664eaf8e Don't manually set b_bufobj, pbgetvp() does this for us. 2004-11-15 08:38:50 +00:00
Poul-Henning Kamp
676f3ee26c Explicitly call pbrelvp() 2004-11-15 08:06:05 +00:00
Poul-Henning Kamp
6e67e2a710 Retire b_magic now, we have the bufobj containing the same hint. 2004-11-04 09:48:18 +00:00
Poul-Henning Kamp
c5995e45eb Lock bp->b_bufobj->b_object instead of bp->b_object 2004-10-28 08:38:46 +00:00
Poul-Henning Kamp
f6b855f60b Avoid using bp->b_vp when we already have the vnode by other means. 2004-10-27 06:45:52 +00:00
Alan Cox
df9f17c3df Synchronize access to the vm page's PG_BUSY flag using the containing vm
object's lock.  In the same place, eliminate unnecessary checks for a NULL
vm object pointer.
2004-10-27 02:05:00 +00:00
Poul-Henning Kamp
b792bebeea Move the buffer method vector (buf->b_op) to the bufobj.
Extend it with a strategy method.

Add bufstrategy() which do the usual VOP_SPECSTRATEGY/VOP_STRATEGY
song and dance.

Rename ibwrite to bufwrite().

Move the two NFS buf_ops to more sensible places, add bufstrategy
to them.

Add inlines for bwrite() and bstrategy() which calls through
buf->b_bufobj->b_ops->b_{write,strategy}().

Replace almost all VOP_STRATEGY()/VOP_SPECSTRATEGY() calls with bstrategy().
2004-10-24 20:03:41 +00:00
Poul-Henning Kamp
494eb176e7 Add b_bufobj to struct buf which eventually will eliminate the need for b_vp.
Initialize b_bufobj for all buffers.

Make incore() and gbincore() take a bufobj instead of a vnode.

Make inmem() local to vfs_bio.c

Change a lot of VI_[UN]LOCK(bp->b_vp) to BO_[UN]LOCK(bp->b_bufobj)
also VI_MTX() to BO_MTX(),

Make buf_vlist_add() take a bufobj instead of a vnode.

Eliminate other uses of bp->b_vp where bp->b_bufobj will do.

Various minor polishing: remove "register", turn panic into KASSERT,
use new function declarations, TAILQ_FOREACH_SAFE() etc.
2004-10-22 08:47:20 +00:00
Poul-Henning Kamp
a76d8f4ec9 Move the VI_BWAIT flag into no bo_flag element of bufobj and call it BO_WWAIT
Add bufobj_wref(), bufobj_wdrop() and bufobj_wwait() to handle the write
count on a bufobj.  Bufobj_wdrop() replaces vwakeup().

Use these functions all relevant places except in ffs_softdep.c where
the use if interlocked_sleep() makes this impossible.

Rename b_vnbufs to b_bobufs now that we touch all the relevant files anyway.
2004-10-21 15:53:54 +00:00
Poul-Henning Kamp
961da2716b Give cluster_write() an explicit vnode argument.
In the future a struct buf will not automatically point out a vnode for us.
2004-09-27 19:14:10 +00:00
Poul-Henning Kamp
cf95b5c381 Eliminate unused second argument to reassignbuf() and simplify it
accordingly.
2004-07-25 21:24:23 +00:00
Warner Losh
7f8a436ff2 Remove advertising clause from University of California Regent's license,
per letter dated July 22, 1999.

Approved by: core
2004-04-05 21:03:37 +00:00
Kirk McKusick
fde81c7d8e Update the statfs structure with 64-bit fields to allow
accurate reporting of multi-terabyte filesystem sizes.

You should build and boot a new kernel BEFORE doing a `make world'
as the new kernel will know about binaries using the old statfs
structure, but an old kernel will not know about the new system
calls that support the new statfs structure. Running an old kernel
after a `make world' will cause programs such as `df' that do a
statfs system call to fail with a bad system call.

Reviewed by:	Bruce Evans <bde@zeta.org.au>
Reviewed by:	Tim Robbins <tjr@freebsd.org>
Reviewed by:	Julian Elischer <julian@elischer.org>
Reviewed by:	the hoards of <arch@freebsd.org>
Sponsored by:   DARPA & NAI Labs.
2003-11-12 08:01:40 +00:00
Alan Cox
f2b1200d08 Initialize the buf's b_object in pbgetvp(). Clear it in pbrelvp(). (This
facilitates synchronization of the vm page's valid field using the
vm object's lock.)

Suggested by:	tegge
2003-10-20 18:24:38 +00:00
Alan Cox
9027d603d3 - Synchronize access to a vm page's valid field using the containing
vm object's lock.
2003-10-20 05:57:55 +00:00
Poul-Henning Kamp
2c18019f14 DuH!
bp->b_iooffset (the spot on the disk), not bp->b_offset (the offset in
the file)
2003-10-18 14:10:28 +00:00
Poul-Henning Kamp
855c6fcc68 Initialize bp->b_offset before calling VOP_STRATEGY() 2003-10-18 11:13:31 +00:00
Jeff Roberson
9dbfeb0ae6 - Move BX_BKGRDWAIT and BX_BKGRDINPROG to BV_ and the b_vflags field.
- Surround all accesses of the BKGRD{WAIT,INPROG} flags with the vnode
   interlock.
 - Don't use the B_LOCKED flag and QUEUE_LOCKED for background write
   buffers.  Check for the BKGRDINPROG flag before recycling or throwing
   away a buffer.  We do this instead because it is not safe for us to move
   the original buffer to a new queue from the callback on the background
   write buffer.
 - Remove the B_LOCKED flag and the locked buffer queue.  They are no longer
   used.
 - The vnode interlock is used around checks for BKGRDINPROG where it may
   not be strictly necessary.  If we hold the buf lock the a back-ground
   write will not be started without our knowledge, one may only be
   completed while we're not looking.  Rather than remove the code, Document
   two of the places where this extra locking is done.  A pass should be
   done to verify and minimize the locking later.
2003-08-28 06:55:18 +00:00
Poul-Henning Kamp
68f2d20b70 Revert stuff which accidentally ended up in the previous commit. 2003-07-22 10:36:36 +00:00
Poul-Henning Kamp
55d1d7034f Don't attempt to inline large functions mb_alloc() and mb_free(),
it more than doubles the text size of this file.

GCC has wisely ignored us on this previously
2003-07-22 10:24:41 +00:00
David E. O'Brien
677b542ea2 Use __FBSDID(). 2003-06-11 00:56:59 +00:00
Poul-Henning Kamp
17a1391990 The IO_NOWDRAIN and B_NOWDRAIN hacks are no longer needed to prevent
deadlocks with vnode backed md(4) devices because md now uses a
kthread to run the bio requests instead of doing it directly from
the bio down path.
2003-05-31 16:42:45 +00:00
Ian Dowse
ad6adb4f18 In cluster_wbuild(), initialise b_iocmd to BIO_WRITE before calling
buf_start() to avoid triggering a panic in softdep_disk_io_initiation()
if b_iocmd happened to be BIO_READ. The later initialisation of
b_iocmd in cluster_wbuild() could probably be moved to before the
buf_start() call, but this patch keeps the change as simple as
possible.

This is reported to fix occasional "softdep_disk_io_initiation: read"
panics, especially on NFS servers.

Reported by:	Nick Hilliard <nick@netability.ie>
Tested by:	Nick Hilliard <nick@netability.ie>
Approved by:	re (rwatson)
2003-05-28 13:22:10 +00:00
Alan Cox
2b7e071e89 - Lock the vm_object when performing vm_object_pip_add(). 2003-04-20 07:29:50 +00:00
Jeff Roberson
abb0e6da6b - We are not guaranteed that read ahead blocks are not in memory already.
Check for B_DELWRI as well as B_CACHED before issuing io on a buffer.  This
   is especially important since we are changing the b_iocmd.
2003-03-30 02:57:32 +00:00
Poul-Henning Kamp
b4b138c27f Including <sys/stdint.h> is (almost?) universally only to be able to use
%j in printfs, so put a newsted include in <sys/systm.h> where the printf
prototype lives and save everybody else the trouble.
2003-03-18 08:45:25 +00:00
Jeff Roberson
5d952c1b59 - Unlock the target bp and not the pager buf bp in a failure case in
cluster_wbuild().  This was causing strange panics that were widely
   reported on current@.

Big Pointy Hat to:	jeff
2003-03-17 18:38:49 +00:00